Method and system for dynamically measuring iron metabolism capability of red blood cells in solid tumor tissue

Abstract

The embodiment of the invention provides a method and a system for dynamically measuring iron metabolism capability of red blood cells in solid tumor tissues, and belongs to the technical field of data processing. The method comprises the following steps: obtaining a first fluorescence image and a first change curve of a first experiment result, and obtaining a second fluorescence image and a second change curve of a second experiment result; performing color correction on the first fluorescence image and the second fluorescence image to obtain a first target image and a second target image; performing abnormal point elimination on the first change curve and the second change curve to obtain a first target curve and a second target curve; performing fluorescence signal analysis on the first target image to obtain a first analysis result; performing fluorescence signal analysis on the second target image to obtain a second analysis result; determining a first distinguishing threshold value according to the first analysis result and the second analysis result; performing curve segmentation on the first target curve and the second target curve to obtain a second distinguishing threshold value; and fusing the first distinguishing threshold and the second distinguishing threshold to determine a target distinguishing threshold.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues. Background Art

[0002] The uptake and full utilization of iron are essential for maintaining cell function and survival. Iron plays an important role in cell biology. It is not only a core component of hemoglobin and myoglobin, but also participates in the active centers of various enzymes and regulates various biochemical reactions. Therefore, iron metabolism homeostasis is crucial for cellular physiological activities. In recent years, significant progress has been made in the study of the mechanism of iron action and its metabolic partner proteins, which has deepened the understanding of the distribution, transport and utilization of iron in cells and revealed a series of protein factors closely related to iron metabolism. These partner proteins play a key regulatory role in the absorption, storage, transport and utilization of iron. In the field of tumor biology, the rapid proliferation of tumor cells requires a large amount of oxygen, which leads to abnormal proliferation of blood vessels and enrichment of red blood cells in tumor tissues. These enriched red blood cells show biochemical characteristics that are significantly different from those of the peripheral blood system in the tumor microenvironment, especially the abnormality of iron metabolism indicators. Therefore, it is of great significance to correctly measure the iron metabolism capacity of red blood cells in tumor tissues, which helps to deeply understand the physiological state of the tumor microenvironment and provide support for the accurate determination of tumor cell staging. However, current technology cannot accurately measure the iron metabolism capacity of red blood cells in solid tumor tissues, which limits the in-depth exploration of their biological behavior.

[0003] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a method and system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues, aiming to solve the problem in the related art that the iron metabolism capacity of red blood cells in solid tumor tissues cannot be accurately measured, thereby limiting the in-depth exploration of their biological behavior.

[0005] In a first aspect, an embodiment of the present invention provides a method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue, comprising:

[0006] Determine a first experimental result corresponding to the detection of an iron metabolism index in relevant red blood cells in a solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object;

[0007] Obtaining a first fluorescent image and a first change curve corresponding to the first experimental result, and obtaining a second fluorescent image and a second change curve corresponding to the second experimental result;

[0008] Performing color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image;

[0009] Eliminate abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve;

[0010] Performing fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells;

[0011] Performing fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood;

[0012] Determine a first discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result;

[0013] Performing curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood;

[0014] The first distinction threshold and the second distinction threshold are fused to determine a target distinction threshold for the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target subject.

[0015] In a second aspect, an embodiment of the present invention provides a system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue, comprising:

[0016] An experimental acquisition module, used to determine a first experimental result corresponding to the detection of iron metabolism indexes in relevant red blood cells in a solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object;

[0017] A data acquisition module, used to obtain a first fluorescent image and a first change curve corresponding to the first experimental result, and to obtain a second fluorescent image and a second change curve corresponding to the second experimental result;

[0018] an image correction module, configured to perform color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image;

[0019] A curve correction module, used for removing abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve;

[0020] A first analysis module, configured to perform fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells;

[0021] A second analysis module, configured to perform fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood;

[0022] A first fusion module, configured to determine a first discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result;

[0023] A third analysis module, configured to perform curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood;

[0024] The second fusion module is used to fuse the first distinction threshold and the second distinction threshold to determine a target distinction threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target object.

[0025] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue provided in the specification of the present invention are implemented.

[0026] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues as provided in the specification of the present invention.

[0027] The embodiment of the present invention provides a method and system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues. The method includes: determining a first experimental result corresponding to the detection of iron metabolism indicators of relevant red blood cells in the solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object; obtaining a first fluorescent image and a first change curve corresponding to the first experimental result, and obtaining a second fluorescent image and a second change curve corresponding to the second experimental result; performing color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image; removing abnormal points from the first change curve and the second change curve. Obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve; perform fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells; perform fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood; determine a first discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result; perform curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood; fuse the first discrimination threshold and the second discrimination threshold to determine the target discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target object. The method ensures the color consistency of the first fluorescent image and the second fluorescent image by color correction. This color correction technology effectively reduces the problem of error in the first discrimination threshold caused by color difference, thereby improving the reliability of data analysis. Then, the first change curve and the second change curve are eliminated for abnormal points to reduce noise interference, thereby not only improving the accuracy of data processing, but also providing strong support for the subsequent improvement of the accuracy of the second discrimination threshold. Finally, by fusing the first discrimination threshold and the second discrimination threshold, the target discrimination threshold of the iron metabolism capacity between the relevant red blood cells and peripheral blood of the target object is determined, thereby providing a scientific basis for distinguishing between healthy and abnormal red blood cells, thereby realizing the accurate measurement of the iron metabolism capacity of red blood cells in solid tumor tissues. This precise measurement method can provide a reliable basis for subsequent treatment of solid tumor tissues, ensuring the pertinence and effectiveness of the treatment plan. In addition, the method has a wide range of applicability and can implement the above steps for different target objects. Each target object corresponds to its own target discrimination threshold, thereby realizing the dynamic measurement of solid tumor tissues. This dynamic measurement feature not only improves the flexibility and adaptability of the method, but also can be personalized according to the specific conditions of different patients. Analysis and processing provide strong support for clinical practice. This method significantly improves the accuracy and scientificity of the measurement of red blood cell iron metabolism capacity in solid tumor tissues, providing important support for precision medicine and personalized treatment.The invention solves the problem that the related technology cannot accurately measure the iron metabolism capacity of red blood cells in solid tumor tissue, thus limiting the in-depth study of their biological behavior. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 A schematic diagram of a process for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues provided by an embodiment of the present invention;

[0030] Figure 2 A schematic diagram of the module structure of a system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues provided by an embodiment of the present invention;

[0031] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0034] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0035] The embodiment of the present invention provides a method and system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue. The method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0036] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0037] Please refer to Figure 1 , Figure 1 A schematic flow chart of a method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue provided by an embodiment of the present invention.

[0038] like Figure 1 As shown, the method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue includes steps S101 to S109.

[0039] Step S101, determining a first experimental result corresponding to the detection of iron metabolism indexes in relevant red blood cells in a solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object.

[0040] Exemplarily, iron metabolism indicators include but are not limited to ferritin, folic acid, intrinsic factor antibodies and the like, and then different iron metabolism indicators are tested to obtain a first experimental result corresponding to the iron metabolism indicator test of relevant red blood cells in solid tumor tissue and a second experimental result corresponding to the ferritin test of the peripheral blood of the solid tumor tissue.

[0041] For example, solid tumor tissue of the target object is obtained by puncture biopsy or surgical resection, and peripheral blood of the target object is obtained by venipuncture. The collected solid tumor tissue is appropriately cut and ground to obtain relevant red blood cells for subsequent testing. The peripheral blood sample is centrifuged to separate red blood cells and serum for ferritin detection. The relevant red blood cells in the solid tumor tissue are labeled with a specific fluorescent dye, and the red blood cells are developed under a fluorescent microscope to obtain the first experimental result. The ferritin content of the serum in the peripheral blood sample is detected using a ferritin detection kit to obtain a second experimental result.

[0042] Step S102: obtaining a first fluorescence image and a first change curve corresponding to the first experimental result, and obtaining a second fluorescence image and a second change curve corresponding to the second experimental result.

[0043] Exemplarily, a first fluorescent image corresponding to the labeled red blood cells is obtained from the first experimental result by fluorescence microscopy, and iron metabolism indicators (such as iron content, transport capacity, etc.) are extracted from the first experimental result to draw a first change curve of the iron metabolism indicators.

[0044] Illustratively, a second fluorescent image of the ferritin content in serum is obtained from the second experimental result by fluorescence microscopy, and iron metabolism indicators (such as iron content, transport capacity, etc.) are extracted from the second experimental result to draw a second change curve of the iron metabolism indicators.

[0045] Step S103: Perform color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image.

[0046] Exemplarily, the first fluorescent image is color corrected by using a histogram equalization and contrast stretching algorithm to obtain a first target image corresponding to the first fluorescent image, and the second fluorescent image is color corrected by using a histogram equalization and contrast stretching algorithm to obtain a second target image corresponding to the second fluorescent image.

[0047] In some embodiments, the color correction of the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image includes: performing normalization coefficient calculation on a filter of color features of the first fluorescent image to obtain a first filter coefficient; applying multiple incremental first Gaussian blurs to the first fluorescent image and recording a first blur processing result corresponding to the first Gaussian blur at each step, fusing the first blur processing results to obtain a first progressive smooth image and a first smooth image corresponding to the first fluorescent image; performing image detail extraction on the first fluorescent image to obtain corresponding first detail information and performing multi-scale decomposition on the first fluorescent image to obtain first decomposition information; fusing the first filter coefficient, the first progressive smooth image, the first smooth image, the first detail information and the first decomposition information to determine a first segmentation threshold corresponding to the first fluorescent image; performing image segmentation on the first fluorescent image according to the first segmentation threshold to obtain a first bright area and a first dim area corresponding to the first fluorescent image; performing color correction on the first bright area and the first dim area respectively to obtain a first correction area corresponding to the first bright area and a second correction area corresponding to the first dim area; The first correction area and the second correction area determine the first target image corresponding to the first fluorescent image; perform normalization coefficient calculation on the filter of the color feature of the second fluorescent image to obtain the second filter coefficient; apply multiple incremental second Gaussian blurs to the second fluorescent image and record the second blur processing results corresponding to each step of the second Gaussian blur, and fuse the second blur processing results to obtain the second asymptotically smoothed image and the second smoothed image corresponding to the second fluorescent image; perform image detail extraction on the second fluorescent image to obtain the corresponding second detail information and perform multi-scale decomposition on the second fluorescent image to obtain the second decomposition information; fuse the second filter coefficient, the second asymptotically smoothed image, the second smoothed image, the second detail information and the second decomposition information to determine the second segmentation threshold corresponding to the second fluorescent image; perform image segmentation on the second fluorescent image according to the second segmentation threshold to obtain the second bright area and the second dim area corresponding to the second fluorescent image; perform color correction on the second bright area and the second dim area respectively to obtain the third correction area corresponding to the second bright area and the fourth correction area corresponding to the second dim area; determine the second target image corresponding to the second fluorescent image according to the third correction area and the fourth correction area.

[0048] Exemplarily, a color feature filter (such as a Gaussian filter, a Laplacian filter, etc.) is determined, and the selected filter is applied to the first fluorescent image and the second fluorescent image respectively to calculate the normalization coefficient to obtain the first filter coefficient and the second filter coefficient.

[0049] For example, the selected color feature filter is multiplied by the pixel value corresponding to the first fluorescent image, and then the results are added to obtain the first feature map after filtering, so as to find the maximum and minimum values ​​of all pixel values ​​in the first feature map, and then the first feature map is normalized according to the minimum and maximum values ​​to obtain the normalized first feature map, so as to determine each pixel value in the normalized first feature map as the first filter coefficient. The first filter coefficient represents the normalized intensity or weight of each pixel in the first fluorescent image after the filter processing. The selected color feature filter is multiplied by the pixel value corresponding to the second fluorescent image, and then the results are added to obtain the second feature map after filtering, so as to find the maximum and minimum values ​​of all pixel values ​​in the second feature map, and then the second feature map is normalized according to the minimum and maximum values ​​to obtain the normalized second feature map, so as to determine each pixel value in the normalized second feature map as the second filter coefficient. The second filter coefficient represents the normalized intensity or weight of each pixel in the second fluorescent image after the filter processing.

[0050] Exemplarily, the blur degree of Gaussian blur is controlled by adjusting the size of the Gaussian kernel, and then the convolution operation is performed on the first fluorescent image by continuously increasing the parameters corresponding to the Gaussian kernel to obtain multiple first blur processing results corresponding to the first fluorescent image, and then the multiple first blur processing results are weighted and fused to obtain a first progressive smooth image, and the minimum data among the multiple first blur processing results is determined as the first smooth image. Similarly, the blur degree of Gaussian blur is controlled by adjusting the size of the Gaussian kernel, and then the convolution operation is performed on the second fluorescent image by continuously increasing the parameters corresponding to the Gaussian kernel to obtain multiple second blur processing results corresponding to the second fluorescent image, and then the multiple second blur processing results are weighted and fused to obtain a second progressive smooth image, and the minimum data among the multiple second blur processing results is determined as the second smooth image.

[0051] Exemplarily, the first fluorescent image is subjected to detail extraction using a Laplacian operator or an edge detection algorithm to obtain first detail information, and the first fluorescent image is subjected to multi-scale decomposition using a multi-scale decomposition algorithm such as a wavelet transform or a Laplacian pyramid to obtain first decomposition information. Similarly, the second fluorescent image is subjected to detail extraction using a Laplacian operator or an edge detection algorithm to obtain second detail information, and the second fluorescent image is subjected to multi-scale decomposition using a multi-scale decomposition algorithm such as a wavelet transform or a Laplacian pyramid to obtain second decomposition information.

[0052] Exemplarily, a first detail quantity corresponding to the first detail information and a first decomposition quantity corresponding to the first decomposition information are obtained, and then the first detail quantity and the first filter coefficient are multiplied to obtain a first product result, and then the first progressive smoothed image and the first smoothed image are added to obtain a first addition result, and the first decomposition quantity and the first fluorescence image are multiplied to obtain a second product result, and finally the first product result and the first addition result are multiplied and divided by the second product result to obtain a first segmentation threshold corresponding to the first fluorescence image.

[0053] Exemplarily, a second detail quantity corresponding to the second detail information and a second decomposition quantity corresponding to the second decomposition information are obtained, and then the second detail quantity and the second filter coefficient are multiplied to obtain a third product result, and then the second progressive smoothed image and the second smoothed image are added to obtain a second addition result, and the second decomposition quantity and the second fluorescence image are multiplied to obtain a fourth product result, and finally the third product result and the second addition result are multiplied and divided by the fourth product result to obtain a second segmentation threshold corresponding to the second fluorescence image.

[0054] Exemplarily, the first fluorescent image is segmented according to a first segmentation threshold to obtain a first bright area and a first dark area corresponding to the first fluorescent image, and the second fluorescent image is segmented according to a second segmentation threshold to obtain a second bright area and a second dark area corresponding to the second fluorescent image.

[0055] Exemplarily, the color information of the first bright area and the first dim area is extracted respectively using a color histogram, an average color value or other color features, so as to analyze the color distribution characteristics of the first bright area and the first dim area according to the color information, identify the possible color deviation or unevenness, and then determine the correction target according to the color characteristics of the first bright area, such as adjusting the brightness, contrast or color temperature to make the color more natural or in line with expectations, so as to correct the first bright area using histogram equalization, color enhancement, brightness contrast adjustment, etc., to generate a first correction area. And according to the color characteristics of the first dim area, a correction target is set to increase the brightness, adjust the saturation, etc., so as to correct the first dim area and generate a second correction area.

[0056] Exemplarily, the color information of the second bright area and the second dim area is extracted respectively using a color histogram, an average color value or other color features, so as to analyze the color distribution characteristics of the second bright area and the second dim area according to the color information, identify the possible color deviation or unevenness, and then determine the correction target according to the color characteristics of the second bright area, such as adjusting the brightness, contrast or color temperature to make the color more natural or in line with expectations, so as to correct the second bright area using histogram equalization, color enhancement, brightness contrast adjustment, etc., to generate a third correction area. And according to the color characteristics of the second dim area, a correction target is set to increase the brightness, adjust the saturation, etc., so as to correct the second dim area and generate a fourth correction area.

[0057] Exemplarily, the first correction area and the second correction area are merged to obtain a first target image corresponding to the first fluorescent image, and the third correction area and the fourth correction area are merged to obtain a second target image corresponding to the second fluorescent image.

[0058] In some embodiments, the color correction of the first bright area and the first dim area is respectively performed to obtain a first correction area corresponding to the first bright area and a second correction area corresponding to the first dim area, including: determining target reference images corresponding to the first bright area and the second bright area, and obtaining a target mean and a target standard deviation corresponding to the target reference images; calculating a first mean and a first standard deviation corresponding to the first bright area; obtaining a first adjustment ratio by dividing the first standard deviation by the target standard deviation, and calculating a first difference between the first bright area and the first mean; determining the first bright area according to the first adjustment ratio, the first difference, and the target mean. The first correction area corresponding to the bright area; obtaining a first probability density function corresponding to the first fluorescent image and a second probability density function corresponding to the target reference image; determining a first conversion function between the first fluorescent image and the target reference image according to the first probability density function and the second probability density function; randomly constructing a first orthogonal matrix, and multiplying the first orthogonal matrix with the first matrix corresponding to the first dim area to obtain a first target matrix; transforming the first target matrix according to the first conversion function to obtain a first transformation matrix; left-multiplying the first transformation matrix and the inverse of the first orthogonal matrix to obtain the second correction area corresponding to the first dim area.

[0059] Exemplarily, based on expert experience or historical experience, a target reference image after staining that can accurately identify iron metabolism index detection is obtained from a database, thereby calculating a target mean and a target standard deviation of the target reference image as a benchmark for color correction.

[0060] Exemplarily, color features are extracted from the first bright area and its first mean and first standard deviation are calculated. The first adjustment ratio is obtained by dividing the first standard deviation by the target standard deviation, and the first difference between each pixel value in the first bright area and the first mean is calculated, so that the first difference and the first adjustment ratio are multiplied and then added to the target mean to obtain the first correction value corresponding to each pixel value in the first bright area, and then the first correction area corresponding to the first bright area is determined according to the first correction value.

[0061] Exemplarily, a color distribution analysis is performed on the first fluorescent image to obtain a corresponding first probability density function, and a color distribution analysis is performed on the target reference image to obtain a corresponding second probability density function, and then a histogram matching technique is used to determine a first conversion function using the first probability density function and the second probability density function so that the color distribution of the first fluorescent image is adjusted to be consistent with the target reference image.

[0062] Exemplarily, a first orthogonal matrix is ​​randomly constructed using a matrix decomposition method, and the first orthogonal matrix is ​​matrix multiplied with the first matrix corresponding to the first dim area to obtain a first target matrix, and then the probability density function corresponding to the first target matrix is ​​substituted into the first conversion function for transformation processing to obtain a first transformation matrix. Finally, the inverse matrix of the first orthogonal matrix is ​​calculated, and the inverse matrix of the first orthogonal matrix is ​​multiplied with the first transformation matrix to obtain a second correction area, so that the first dim area achieves color correction while maintaining the original distribution of the first dim area.

[0063] In some embodiments, the color correction of the second bright area and the second dim area respectively to obtain a third correction area corresponding to the second bright area and a fourth correction area corresponding to the second dim area includes: calculating a second mean and a second standard deviation corresponding to the second bright area; obtaining a second adjustment ratio by dividing the second standard deviation by the target standard deviation, and calculating a second difference between the second bright area and the second mean; determining the third correction area corresponding to the second bright area according to the second adjustment ratio, the second difference and the target mean; obtaining a third probability density function corresponding to the second fluorescent image; determining a second conversion function between the second fluorescent image and the target reference image according to the third probability density function and the second probability density function; randomly constructing a second orthogonal matrix, and multiplying the second orthogonal matrix by the second matrix corresponding to the second dim area to obtain a second target matrix; transforming the second target matrix according to the second conversion function to obtain a second transformation matrix; left-multiplying the second transformation matrix by the inverse of the second orthogonal matrix to obtain the fourth correction area corresponding to the second dim area.

[0064] Exemplarily, based on expert experience or historical experience, a target reference image after staining that can accurately identify iron metabolism index detection is obtained from a database, thereby calculating a target mean and a target standard deviation of the target reference image as a benchmark for color correction.

[0065] Exemplarily, color features are extracted from the second bright area and its second mean and second standard deviation are calculated. The second adjustment ratio is obtained by dividing the second standard deviation by the target standard deviation, and the second difference between each pixel value in the second bright area and the second mean is calculated, so that the second difference and the second adjustment ratio are multiplied and then added to the target mean to obtain the second correction value corresponding to each pixel value in the second bright area, and then the third correction area corresponding to the second bright area is determined according to the second correction value.

[0066] Exemplarily, a color distribution analysis is performed on the second fluorescent image to obtain a corresponding third probability density function, and a color distribution analysis is performed on the target reference image to obtain a corresponding second probability density function, and then a histogram matching technique is used to determine a second conversion function using the third probability density function and the second probability density function so that the color distribution of the second fluorescent image is adjusted to be consistent with the target reference image.

[0067] Exemplarily, a second orthogonal matrix is ​​randomly constructed using a matrix decomposition method, and the second orthogonal matrix is ​​matrix multiplied with the second matrix corresponding to the second dim area to obtain a second target matrix, and then the probability density function corresponding to the second target matrix is ​​substituted into the second conversion function for transformation processing to obtain a second transformation matrix. Finally, the inverse matrix of the second orthogonal matrix is ​​calculated, and the inverse matrix of the second orthogonal matrix is ​​multiplied with the second transformation matrix to obtain a fourth correction area, so that the second dim area achieves color correction while maintaining the original distribution of the second dim area.

[0068] Step S104: removing abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve.

[0069] Exemplarily, an anomaly detection method such as a standard deviation detection algorithm or an anomaly detection algorithm using an isolation forest is applied to the data points of the first change curve and the second change curve respectively to identify a first anomaly point corresponding to the first change curve and a second anomaly point corresponding to the second change curve.

[0070] Exemplarily, the first change curve data after the first abnormal point is removed is interpolated or smoothed to generate a continuous first target curve, and the second change curve data after the second abnormal point is removed is interpolated or smoothed to generate a continuous second target curve.

[0071] In some embodiments, the removing of abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve includes: discretizing the first change curve to obtain first discrete data and discretizing the second change curve to obtain second discrete data; obtaining a first neighbor point corresponding to each first data in the first discrete data, and calculating a first average distance between the first neighbor point and the first data; calculating a first similarity between any two first data according to the first average distance, and fusing the first similarity between the first data and the remaining data in the first discrete data to determine a first target similarity corresponding to the first data; screening the first discrete data according to the first target similarity to obtain first abnormal data; obtaining a second neighbor point corresponding to each second data in the second discrete data, And calculate the second average distance between the second neighbor point and the second data; calculate the second similarity between any two of the second data according to the second average distance, and fuse the second similarity between the second data and the remaining data in the second discrete data to determine the second target similarity corresponding to the second data; screen the second discrete data according to the second target similarity to obtain second abnormal data; perform abnormal analysis on the first abnormal data to obtain first target abnormal data corresponding to the first abnormal data; perform abnormal analysis on the second abnormal data to obtain second target abnormal data corresponding to the second abnormal data; remove abnormal points from the first change curve according to the first target abnormal data to obtain the first target curve corresponding to the first change curve; remove abnormal points from the second change curve according to the second target abnormal data to obtain the second target curve corresponding to the second change curve.

[0072] Exemplarily, the first change curve is converted into a discrete data point set to obtain first discrete data, and the second change curve is converted into a discrete data point set to obtain second discrete data.

[0073] Exemplarily, the distance between each first data in the first discrete data and other data in the first discrete data is calculated, and then the data with the smallest distance is determined as the first neighbor point corresponding to the first data, so that the first distance and the distance between the first neighbor points are summed and averaged to obtain the first average distance between the first neighbor point and the first data. The first neighbor point is one or more data with a small distance between the first data and other data in the first discrete data.

[0074] Exemplarily, the above steps are performed on each first data in the first discrete data to obtain the first average distance corresponding to each first data, and then the maximum and minimum values ​​of the two first average distances corresponding to any two first data in the first discrete data are solved, and then the minimum value between the two first average distances and the maximum value between the two first average distances are divided to obtain the first similarity between any two first data. Therefore, when the difference between the first average distances between the two first data is smaller, the first similarity is greater, that is, the greater the ratio between the minimum value and the maximum value, the smaller the difference between the two first data, and the greater the first similarity.

[0075] Exemplarily, after calculating the first similarity between each first data and other data in the first discrete data, all first similarities between the first data and other data in the first discrete data are summed to obtain the first target similarity between the first data and other data in the first discrete data.

[0076] Exemplarily, a preset threshold is determined based on historical experience or expert experience, and the preset threshold is compared with the first target similarity. When the first target similarity is less than the preset threshold, the first data corresponding to the first target similarity is determined as the first abnormal data.

[0077] Exemplarily, the distance between each second data in the second discrete data and other data in the second discrete data is calculated, and then the data with the smallest distance is determined as the second nearest neighbor point corresponding to the second data, so that the second distance and the distance between the second nearest neighbor points are summed and averaged to obtain the second average distance between the second nearest neighbor point and the second data. The second nearest neighbor point is one or more data with a small distance between the second data and other data in the second discrete data.

[0078] Exemplarily, the above steps are performed on each second data in the second discrete data to obtain the second average distance corresponding to each second data, and then the maximum and minimum values ​​of the two second average distances corresponding to any two second data in the second discrete data are solved, and then the minimum value between the two second average distances and the maximum value between the two second average distances are divided to obtain the second similarity between any two second data. Thus, when the difference between the second average distances between the two second data is smaller, the second similarity is greater, that is, the greater the ratio between the minimum value and the maximum value, the smaller the difference between the two second data, and the greater the second similarity.

[0079] Exemplarily, after calculating the second similarity between each second data and other data in the second discrete data, all second similarities between the second data and other data in the second discrete data are summed to obtain the second target similarity between the second data and other data in the second discrete data.

[0080] Exemplarily, a preset threshold is determined based on historical experience or expert experience, and the preset threshold is compared with the second target similarity. When the second target similarity is less than the preset threshold, the second data corresponding to the second target similarity is determined as second abnormal data.

[0081] Exemplarily, the first abnormal data is further identified for abnormality according to the abnormality identification model, the truly abnormal part is identified, and the first target abnormal data is obtained; and the second abnormal data is further analyzed for abnormality using the abnormality identification model, the truly abnormal part is identified, and the second target abnormal data is obtained.

[0082] Exemplarily, according to the first target abnormal data, the abnormal points in the first change curve are removed to generate the first target curve. And according to the second target abnormal data, the abnormal points in the second change curve are removed to generate the second target curve.

[0083] In some embodiments, performing anomaly analysis on the first abnormal data to obtain first target abnormal data corresponding to the first abnormal data includes: obtaining a third neighbor point corresponding to each third data in the first abnormal data, and obtaining a fourth neighbor point corresponding to each third neighbor point; calculating a first distance between the third neighbor point and the fourth neighbor point, and determining a first neighbor representation distance corresponding to the third data according to the first distance; obtaining an intersection between the fourth neighbor point and the third data, obtaining first identical data, and determining first weight information corresponding to the third data according to the first identical data; determining a first abnormal value corresponding to the third data according to the first neighbor representation distance and the first weight information; performing abnormal screening on the first abnormal data according to the first abnormal value to obtain the corresponding first target abnormal data; wherein the first abnormal value is obtained according to the following formula:

[0084]

[0085] Among them, value 1i represents the first abnormal value corresponding to the i-th third data, n represents the number of neighbors corresponding to the third neighbor point, x 1ik represents the kth third neighbor point of the i-th third data, represents the kth fourth nearest neighbor point of the kth third nearest neighbor point, represents the first distance between the kth third neighbor point of the i-th third data and the kth fourth neighbor point of the kth third neighbor point, dis(i, x 1ik) represents the kth third neighboring point x of the i-th third data and the i-th third data 1ik The third distance between represents the first nearest neighbor representation distance, w 1i Represents the first weight information corresponding to the i-th third data.

[0086] Exemplarily, for each third data in the first abnormal data, find the nearest neighboring point set of the third data to obtain the third nearest neighbor point. Then for each third nearest neighbor point, find the nearest neighboring point set of the third nearest neighbor point to obtain the fourth nearest neighbor point, and then calculate the distance between the third nearest neighbor point and the fourth nearest neighbor point according to the distance calculation formula and record it as the first distance. Then calculate the third distance between the third data and the third nearest neighbor point according to the distance calculation formula, so as to determine the first nearest neighbor representation distance corresponding to the third data according to the first distance and the third distance. For example, the first nearest neighbor representation distance is obtained according to the following formula:

[0087]

[0088] Among them, b 1ik The first nearest neighbor representation distance corresponding to the kth first nearest neighbor point of the i-th third data, dis(i,x 1ik ) represents the kth third neighbor point x of the i-th third data and the i-th third data 1ik The third distance between Represents the first distance between the kth third nearest neighbor point of the i-th third data and the kth fourth nearest neighbor point of the kth third nearest neighbor point. k is a positive integer.

[0089] Exemplarily, the fourth nearest neighbor is the nearest neighbor of the third nearest neighbor obtained by performing a nearest neighbor calculation on each third nearest neighbor. Thus, the fourth nearest neighbor and the third data are intersected, that is, it is determined whether the nearest neighbor of the third nearest neighbor includes the third data, that is, whether the third data and the third nearest neighbor are mutually nearest neighbors. If the third data and the third nearest neighbor are mutually nearest neighbors, the first identical data is the corresponding nearest neighbor position of the third data in the fourth nearest neighbor. If the third data and the third nearest neighbor are not mutually nearest neighbors, the first identical data is 0.

[0090] For example, the three closest neighboring points of the third data x are determined as the third nearest neighboring points x1, x2, and x3, and then the three closest fourth nearest neighboring points x11, x12, and x13 are obtained for the third nearest neighboring point x1, and the three closest fourth nearest neighboring points x21, x22, and x23 are obtained for the third nearest neighboring point x2, and the three closest fourth nearest neighboring points x31, x32, and x33 are obtained for the third nearest neighboring point x3. If the fourth nearest neighboring points x11, x12, and x13 corresponding to the third nearest neighboring point x1 have the same point as the third nearest neighboring point x1, then the third data x and the third nearest neighboring point x1 are neighboring points to each other, and if the fourth nearest neighboring point x11 is the same point as the third data x, then the first identical data is the fourth nearest neighboring point x11.

[0091] Exemplarily, all the first identical data corresponding to the third data are obtained, thereby obtaining the neighbor position of the first identical data in the fourth neighbor point, and then the neighbor positions are summed and then added by 1 to obtain the sum result, and then the sum result is divided by the maximum number of neighbors to obtain the first weight information. The purpose of adding 1 is to prevent the first weight information from being 0. The neighbor position is the neighbor subscript of the third data in the fourth neighbor point, that is, the neighbor position is the neighbor rank of the third data as the third neighbor point. For example, if the third data is the third neighbor number of the third neighbor point, the neighbor position is 3, and if the third data is the fourth neighbor number of the third neighbor point, the neighbor position is 4.

[0092] For example, the first identical data is the fourth neighbor point x11, which indicates that the third data is the first neighbor point of the third neighbor point x1, and the neighbor position is 1.

[0093] Exemplarily, the first outlier corresponding to the third data is determined by fusing the first nearest neighbor representation distance and the first weight information according to the following formula:

[0094]

[0095] in, represents the first abnormal value corresponding to the i-th third data, n represents the number of neighbors corresponding to the third nearest neighbor point, x 1ik represents the kth third nearest neighbor point of the i-th third data, represents the kth fourth nearest neighbor of the kth third nearest neighbor, represents the first distance between the kth third nearest neighbor point of the i-th third data and the kth fourth nearest neighbor point of the kth third nearest neighbor point, dis(i,x 1ik ) represents the kth third neighbor point x of the i-th third data and the i-th third data 1ik The third distance between represents the first nearest neighbor representation distance, w 1i Represents the first weight information corresponding to the i-th third data.

[0096] Exemplarily, the difference between the third data and other data can be determined according to the above formula, so as to better measure the abnormality of the third data relative to other data. Thus, the first abnormal data are sorted from low to high according to the first abnormal value, so as to determine the first h first abnormal data as the first target abnormal data, where h is the number of abnormalities of the first target abnormal data.

[0097] In some embodiments, performing anomaly analysis on the second abnormal data to obtain second target abnormal data corresponding to the second abnormal data includes: obtaining a fifth neighbor point corresponding to each fourth data in the second abnormal data, and obtaining a sixth neighbor point corresponding to each fifth neighbor point; calculating a second distance between the fifth neighbor point and the sixth neighbor point, and determining a second neighbor representation distance corresponding to the fourth data according to the second distance; obtaining an intersection between the sixth neighbor point and the fourth data, obtaining second identical data, and determining second weight information corresponding to the fourth data according to the second identical data; determining a second abnormal value corresponding to the fourth data according to the second neighbor representation distance and the second weight information; performing abnormal screening on the second abnormal data according to the second abnormal value to obtain the corresponding second target abnormal data; wherein the second abnormal value is obtained according to the following formula:

[0098]

[0099] in, represents the second abnormal value corresponding to the jth fourth data, m represents the number of neighbors corresponding to the fifth nearest neighbor point, represents the kth fifth nearest neighbor point of the jth fourth data, represents the kth sixth nearest neighbor point of the kth fifth nearest neighbor point, represents the second distance between the kth fifth neighbor point of the jth fourth data and the kth sixth neighbor point of the kth fifth neighbor point, Indicates the kth fifth neighbor point of the jth fourth data and the jth fourth data The fourth distance between represents the second nearest neighbor representation distance, Represents the second weight information corresponding to the j-th fourth data.

[0100] Exemplarily, for each fourth data in the second abnormal data, find the nearest neighboring point set of the fourth data to obtain the fifth nearest neighboring point. Then for each fifth nearest neighboring point, find the nearest neighboring point set of the fifth nearest neighboring point to obtain the sixth nearest neighboring point, and then calculate the distance between the fifth nearest neighboring point and the sixth nearest neighboring point according to the distance calculation formula and record it as the second distance. Then calculate the fourth distance between the fourth data and the fifth nearest neighboring point according to the distance calculation formula, so as to determine the second nearest neighbor characterization distance corresponding to the fourth data according to the second distance and the fourth distance. For example, the second nearest neighbor characterization distance is obtained according to the following formula:

[0101]

[0102] Among them, b 1jk Indicates the second nearest neighbor representation distance corresponding to the kth fifth nearest neighbor point of the jth fourth data, represents the second distance between the kth fifth nearest neighbor point of the jth fourth data and the kth sixth nearest neighbor point of the kth fifth nearest neighbor point, Indicates the kth fifth neighbor point of the jth fourth data and the jth fourth data The fourth distance between represents the second nearest neighbor representation distance, and k is a positive integer.

[0103] Exemplarily, the sixth nearest neighbor is the nearest neighbor of the fifth nearest neighbor obtained by performing a nearest neighbor calculation on each fifth nearest neighbor. Thus, the sixth nearest neighbor and the fourth data are intersected, that is, it is determined whether the nearest neighbor of the fifth nearest neighbor includes the fourth data, that is, whether the fourth data and the fifth nearest neighbor are mutually nearest neighbors. If the fourth data and the fifth nearest neighbor are mutually nearest neighbors, the second identical data is the nearest neighbor position corresponding to the fourth data in the sixth nearest neighbor. If the fourth data and the fifth nearest neighbor are not mutually nearest neighbors, the first identical data is 0.

[0104] Exemplarily, all the second identical data corresponding to the fourth data are obtained, so as to obtain the neighbor position of the second identical data in the sixth neighbor point, and then the neighbor positions are summed and then added by 1 to obtain the sum result, and then the sum result is divided by the maximum number of neighbors to obtain the second weight information. The purpose of adding 1 is to prevent the second weight information from being 0. The neighbor position is the neighbor subscript of the fourth data in the sixth neighbor point, that is, the neighbor position is the neighbor rank of the fourth data as the fifth neighbor point. For example, if the fourth data is the third neighbor number of the fifth neighbor point, the neighbor position is 3, and if the third data is the fourth neighbor number of the fifth neighbor point, the neighbor position is 4.

[0105] Exemplarily, the second outlier corresponding to the fourth data is determined by fusing the second nearest neighbor representation distance and the second weight information according to the following formula:

[0106]

[0107] in, represents the second abnormal value corresponding to the jth fourth data, m represents the number of neighbors corresponding to the fifth nearest neighbor point, represents the kth fifth nearest neighbor point of the jth fourth data, represents the kth sixth nearest neighbor of the kth fifth nearest neighbor, represents the second distance between the kth fifth nearest neighbor point of the jth fourth data and the kth sixth nearest neighbor point of the kth fifth nearest neighbor point, Indicates the kth fifth neighbor point of the jth fourth data and the jth fourth data The fourth distance between represents the second nearest neighbor representation distance, Represents the second weight information corresponding to the j-th fourth data.

[0108] Exemplarily, the degree of difference between the fourth data and other data can be determined according to the above formula, so as to better measure the degree of abnormality of the fourth data relative to other data. Thus, the second abnormal data are sorted from low to high according to the second abnormal value, so as to determine the first h second abnormal data as the second target abnormal data, where h is the number of abnormalities of the second target abnormal data.

[0109] Step S105 , performing fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells.

[0110] Exemplarily, red blood cells are separated from the first target image according to edge detection, thereby calculating the fluorescence intensity in each red blood cell region, and then based on the known relationship between iron metabolism capacity and fluorescence intensity, a mapping model is established, thereby using the established mapping model to convert the extracted fluorescence intensity into a first analysis result of iron metabolism capacity. The first analysis result can be range information such as iron metabolism rate, iron storage, and iron utilization efficiency, that is, the first analysis result is the data range of the iron metabolism capacity of the relevant red blood cells.

[0111] Step S106: performing fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood.

[0112] Exemplarily, red blood cells are separated from the second target image according to edge detection, thereby calculating the fluorescence intensity in each red blood cell region, and then based on the known relationship between iron metabolism capacity and fluorescence intensity, a mapping model is established, thereby using the established mapping model to convert the extracted fluorescence intensity into a second analysis result of iron metabolism capacity. The second analysis result can be range information such as iron metabolism rate, iron storage, and iron utilization efficiency, that is, the second analysis result is the data range of the iron metabolism capacity of peripheral blood.

[0113] Step S107: determining a first distinction threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result.

[0114] Exemplarily, the intersection of the first analysis result and the second analysis result is calculated to obtain an intersection result. If the intersection result is not an empty set, the remaining range after removing the intersection result from the first analysis result is determined as the first discrimination threshold. If the intersection result is an empty set, the minimum and maximum values ​​in the first analysis result and the second analysis result are obtained, and then the minimum and maximum values ​​are combined to form a third analysis result, and then the remaining range after removing the first analysis result and the second analysis result from the third analysis result is determined as the first discrimination threshold.

[0115] Step S108: performing curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood.

[0116] Exemplarily, it is ensured that the data points of the first target curve and the second target curve are aligned in time and iron metabolic capacity to allow for effective comparison and analysis.

[0117] Exemplarily, the first target curve and the second target curve are analyzed to find key characteristic points. These characteristic points may be the peak value, valley value, inflection point, slope change point, etc. of the curve, and then the extracted characteristic points are calculated to obtain characteristic values. For example, the slope, curvature, peak height, etc. of the characteristic points are calculated. According to the extracted characteristic values ​​and characteristic points, the segmentation points of the first target curve and the second target curve are determined. These segmentation points should be positions that can clearly distinguish the two curves. The curve is segmented at the determined segmentation points to form multiple sub-curves. These sub-curves will respectively represent the iron metabolism capacity of the relevant red blood cells and peripheral blood at different times or variable ranges.

[0118] Exemplarily, the segmented sub-curves are compared to analyze their differences at different times or within variable ranges. These differences can help determine the change pattern of the iron metabolism capacity between the relevant red blood cells and the peripheral blood, thereby determining the second distinction threshold, which can effectively distinguish the difference in iron metabolism capacity between the relevant red blood cells and the peripheral blood. The second distinction threshold is also a variable range.

[0119] Step S109: The first distinction threshold and the second distinction threshold are integrated to determine a target distinction threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target object.

[0120] Exemplarily, the first distinction threshold and the second distinction threshold are intersected and calculated, so that the intersection result is determined as the target distinction threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target object.

[0121] See also Figure 2 , Figure 2 A system 200 for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues provided in an embodiment of the present application includes an experimental acquisition module 201, a data acquisition module 202, an image correction module 203, a curve correction module 204, a first analysis module 205, a second analysis module 206, a first fusion module 207, a third analysis module 208, and a second fusion module 209, wherein the experimental acquisition module 201 is used to determine a first experimental result corresponding to the iron metabolism index detection of relevant red blood cells in the solid tumor tissue of the target object and a second experimental result corresponding to the ferritin detection of the peripheral blood of the solid tumor tissue of the target object; the data acquisition module 202 is used to obtain a first fluorescent image and a first change curve corresponding to the first experimental result, and to obtain a second fluorescent image and a second change curve corresponding to the second experimental result; the image correction module 203 is used to perform color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image. two target images; a curve correction module 204, used to remove abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve; a first analysis module 205, used to perform fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells; a second analysis module 206, used to perform fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood; a first fusion module 207, used to determine a first distinction threshold for the iron metabolism capacity between the relevant red blood cells and the peripheral blood based on the first analysis result and the second analysis result; a third analysis module 208, used to perform curve segmentation on the first target curve and the second target curve to obtain a second distinction threshold for the iron metabolism capacity between the relevant red blood cells and the peripheral blood; a second fusion module 209, used to fuse the first distinction threshold and the second distinction threshold to determine the target distinction threshold for the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target object.

[0122] In some embodiments, the system 200 for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues can be applied to a terminal device.

[0123] It should be noted that those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system 200 for dynamically measuring the iron metabolic capacity of red blood cells in solid tumor tissues described above can refer to the corresponding process in the aforementioned method embodiment for dynamically measuring the iron metabolic capacity of red blood cells in solid tumor tissues, and will not be repeated here.

[0124] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0125] like Figure 3 As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0126] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0127] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0128] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0129] The processor is used to run the computer program stored in the memory, and implement any one of the methods for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues provided by the embodiments of the present invention when executing the computer program.

[0130] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0131] Determine a first experimental result corresponding to the detection of an iron metabolism index in relevant red blood cells in a solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object;

[0132] Obtaining a first fluorescent image and a first change curve corresponding to the first experimental result, and obtaining a second fluorescent image and a second change curve corresponding to the second experimental result;

[0133] Performing color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image;

[0134] Eliminate abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve;

[0135] Performing fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells;

[0136] Performing fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood;

[0137] Determine a first discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result;

[0138] Performing curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood;

[0139] The first distinction threshold and the second distinction threshold are fused to determine a target distinction threshold for the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target subject.

[0140] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned method embodiment for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues, and will not be repeated here.

[0141] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues as provided in the description of the embodiments of the present invention.

[0142] The storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device.

[0143] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0144] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0145] The serial numbers of the embodiments of the present invention above are only for description and do not represent the superiority or inferiority of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue, characterized in that: The method comprises: Determine a first experimental result corresponding to the detection of an iron metabolism index in relevant red blood cells in a solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object; Obtaining a first fluorescent image and a first change curve corresponding to the first experimental result, and obtaining a second fluorescent image and a second change curve corresponding to the second experimental result; Performing color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image; Eliminate abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve; Performing fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells; Performing fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood; Determine a first discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result; Performing curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood; The first distinction threshold and the second distinction threshold are fused to determine a target distinction threshold for the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target subject.

2. The method according to claim 1, characterized in that: The color correction of the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image includes: Performing normalization coefficient calculation on a filter of color characteristics of the first fluorescent image to obtain a first filter coefficient; Applying multiple incremental first Gaussian blurs to the first fluorescent image and recording a first blur processing result corresponding to the first Gaussian blur at each step, and fusing the first blur processing results to obtain a first progressive smoothed image and a first smoothed image corresponding to the first fluorescent image; Performing image detail extraction on the first fluorescent image to obtain corresponding first detail information and performing multi-scale decomposition on the first fluorescent image to obtain first decomposition information; Determine a first segmentation threshold corresponding to the first fluorescent image by fusing the first filter coefficient, the first asymptotically smoothed image, the first smoothed image, the first detail information, and the first decomposition information; Performing image segmentation on the first fluorescent image according to the first segmentation threshold to obtain a first bright area and a first dark area corresponding to the first fluorescent image; Performing color correction on the first bright area and the first dim area respectively to obtain a first correction area corresponding to the first bright area and a second correction area corresponding to the first dim area; Determine the first target image corresponding to the first fluorescent image according to the first correction area and the second correction area; Performing normalization coefficient calculation on a filter of color characteristics of the second fluorescent image to obtain a second filter coefficient; Applying multiple incremental second Gaussian blurs to the second fluorescent image and recording a second blur processing result corresponding to each step of the second Gaussian blur, fusing the second blur processing results to obtain a second asymptotically smoothed image and a second smoothed image corresponding to the second fluorescent image; performing image detail extraction on the second fluorescent image to obtain corresponding second detail information and performing multi-scale decomposition on the second fluorescent image to obtain second decomposition information; Determine a second segmentation threshold corresponding to the second fluorescent image by fusing the second filter coefficient, the second asymptotically smoothed image, the second smoothed image, the second detail information, and the second decomposition information; Performing image segmentation on the second fluorescent image according to the second segmentation threshold to obtain a second bright area and a second dark area corresponding to the second fluorescent image; Performing color correction on the second bright area and the second dim area respectively to obtain a third correction area corresponding to the second bright area and a fourth correction area corresponding to the second dim area; The second target image corresponding to the second fluorescent image is determined according to the third correction area and the fourth correction area.

3. The method according to claim 2, characterized in that The performing color correction on the first bright area and the first dim area respectively to obtain a first correction area corresponding to the first bright area and a second correction area corresponding to the first dim area includes: Determine target reference images corresponding to the first bright area and the second bright area, and obtain a target mean and a target standard deviation corresponding to the target reference images; Calculating a first mean and a first standard deviation corresponding to the first bright area; Obtaining a first adjustment ratio by dividing the first standard deviation by the target standard deviation, and calculating a first difference between the first bright area and the first mean value; determining the first correction area corresponding to the first bright area according to the first adjustment ratio, the first difference and the target mean; Obtaining a first probability density function corresponding to the first fluorescent image and a second probability density function corresponding to the target reference image; determining a first conversion function between the first fluorescent image and the target reference image according to the first probability density function and the second probability density function; randomly constructing a first orthogonal matrix, and multiplying the first orthogonal matrix with a first matrix corresponding to the first dim area to obtain a first target matrix; Performing transformation processing on the first target matrix according to the first conversion function to obtain a first transformation matrix; The first transformation matrix and the inverse of the first orthogonal matrix are left-multiplied to obtain the second correction area corresponding to the first dim area.

4. The method according to claim 3, characterized in that: The color correction is performed on the second bright area and the second dim area to obtain a third correction area corresponding to the second bright area and a fourth correction area corresponding to the second dim area, including: Calculate a second mean and a second standard deviation corresponding to the second bright area; Obtaining a second adjustment ratio by dividing the second standard deviation by the target standard deviation, and calculating a second difference between the second bright area and the second mean; determining the third correction area corresponding to the second bright area according to the second adjustment ratio, the second difference and the target mean; Obtaining a third probability density function corresponding to the second fluorescent image; determining a second conversion function between the second fluorescent image and the target reference image according to the third probability density function and the second probability density function; randomly constructing a second orthogonal matrix, and multiplying the second orthogonal matrix with a second matrix corresponding to the second dim area to obtain a second target matrix; Performing transformation processing on the second target matrix according to the second conversion function to obtain a second transformation matrix; The second transformation matrix and the inverse of the second orthogonal matrix are left-multiplied to obtain the fourth correction area corresponding to the second dim area.

5. The method according to claim 1, characterized in that The step of removing abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve includes: Discretizing the first change curve to obtain first discrete data and discretizing the second change curve to obtain second discrete data; Obtaining a first neighbor point corresponding to each first data in the first discrete data, and calculating a first average distance between the first neighbor point and the first data; Calculate the first similarity between any two of the first data according to the first average distance, and fuse the first similarity between the first data and the remaining data in the first discrete data to determine the first target similarity corresponding to the first data; Screening the first discrete data according to the first target similarity to obtain first abnormal data; Obtaining a second neighboring point corresponding to each second data in the second discrete data, and calculating a second average distance between the second neighboring point and the second data; Calculate the second similarity between any two of the second data according to the second average distance, and fuse the second similarity between the second data and the remaining data in the second discrete data to determine the second target similarity corresponding to the second data; Screening the second discrete data according to the second target similarity to obtain second abnormal data; Performing an abnormality analysis on the first abnormal data to obtain first target abnormal data corresponding to the first abnormal data; Performing an abnormality analysis on the second abnormal data to obtain second target abnormal data corresponding to the second abnormal data; Eliminate abnormal points from the first change curve according to the first target abnormal data to obtain the first target curve corresponding to the first change curve; The second target curve corresponding to the second change curve is obtained by removing abnormal points from the second change curve according to the second target abnormal data.

6. The method according to claim 5, characterized in that The performing anomaly analysis on the first abnormal data to obtain first target abnormal data corresponding to the first abnormal data includes: Obtain a third nearest neighbor point corresponding to each third data in the first abnormal data, and obtain a fourth nearest neighbor point corresponding to each third nearest neighbor point; Calculating a first distance between the third nearest neighbor point and the fourth nearest neighbor point, and determining a first nearest neighbor representation distance corresponding to the third data according to the first distance; Obtaining an intersection between the fourth neighbor point and the third data to obtain first identical data, and determining first weight information corresponding to the third data according to the first identical data; Determine a first outlier corresponding to the third data according to the first neighbor representation distance and the first weight information; Performing abnormal screening on the first abnormal data according to the first abnormal value to obtain the corresponding first target abnormal data; The first abnormal value is obtained according to the following formula: Among them, value 1i represents the first abnormal value corresponding to the i-th third data, n represents the number of neighbors corresponding to the third neighbor point, x 1ik represents the kth third neighbor point of the i-th third data, y 1kk represents the kth fourth nearest neighbor point of the kth third nearest neighbor point, represents the first distance between the kth third neighbor point of the i-th third data and the kth fourth neighbor point of the kth third neighbor point, dis(i, x 1ik ) represents the kth third neighboring point x of the i-th third data and the i-th third data 1ik The third distance between represents the first nearest neighbor representation distance, w 1i Represents the first weight information corresponding to the i-th third data.

7. The method according to claim 5, characterized in that The performing anomaly analysis on the second abnormal data to obtain second target abnormal data corresponding to the second abnormal data includes: Obtain a fifth neighbor point corresponding to each fourth data in the second abnormal data, and obtain a sixth neighbor point corresponding to each fifth neighbor point; Calculating a second distance between the fifth nearest neighbor point and the sixth nearest neighbor point, and determining a second nearest neighbor representation distance corresponding to the fourth data according to the second distance; Obtaining an intersection between the sixth nearest neighbor point and the fourth data to obtain second identical data, and determining second weight information corresponding to the fourth data according to the second identical data; Determine a second outlier corresponding to the fourth data according to the second nearest neighbor representation distance and the second weight information; Performing anomaly screening on the second abnormal data according to the second abnormal value to obtain the corresponding second target abnormal data; The second abnormal value is obtained according to the following formula: Among them, value 2j represents the second abnormal value corresponding to the jth fourth data, m represents the number of neighbors corresponding to the fifth nearest neighbor point, x 2jk represents the kth fifth neighbor point of the jth fourth data, y 2kk represents the kth sixth nearest neighbor point of the kth fifth nearest neighbor point, represents the second distance between the kth fifth neighbor point of the jth fourth data and the kth sixth neighbor point of the kth fifth neighbor point, Indicates the kth fifth neighbor point of the jth fourth data and the jth fourth data The fourth distance between represents the second nearest neighbor representation distance, w 2j Represents the second weight information corresponding to the j-th fourth data.

8. A system for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues, characterized in that: include: An experimental acquisition module, used to determine a first experimental result corresponding to the detection of iron metabolism indexes in relevant red blood cells in a solid tumor tissue of a target object and a second experimental result corresponding to the detection of ferritin in the peripheral blood of the solid tumor tissue of the target object; A data acquisition module, used to obtain a first fluorescent image and a first change curve corresponding to the first experimental result, and to obtain a second fluorescent image and a second change curve corresponding to the second experimental result; an image correction module, configured to perform color correction on the first fluorescent image and the second fluorescent image to obtain a first target image corresponding to the first fluorescent image and a second target image corresponding to the second fluorescent image; A curve correction module, used for removing abnormal points from the first change curve and the second change curve to obtain a first target curve corresponding to the first change curve and a second target curve corresponding to the second change curve; A first analysis module, configured to perform fluorescence signal analysis on the first target image to obtain a first analysis result corresponding to the iron metabolism capacity of the relevant red blood cells; A second analysis module, configured to perform fluorescence signal analysis on the second target image to obtain a second analysis result corresponding to the iron metabolism capacity of the peripheral blood; A first fusion module, configured to determine a first discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood according to the first analysis result and the second analysis result; A third analysis module, configured to perform curve segmentation on the first target curve and the second target curve to obtain a second discrimination threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood; The second fusion module is used to fuse the first distinction threshold and the second distinction threshold to determine a target distinction threshold of the iron metabolism capacity between the relevant red blood cells and the peripheral blood of the target object.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissue according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for dynamically measuring the iron metabolism capacity of red blood cells in solid tumor tissues according to any one of claims 1 to 7.

Images